DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

TL;DR

This paper introduces DG-PIC, a novel model for domain-generalized point cloud understanding that handles multiple tasks and domains without model updates, significantly outperforming existing methods.

Contribution

The paper proposes DG-PIC, a unified approach with dual-level prototype estimation and feature shifting for multi-task, multi-domain point cloud understanding without test-time model updates.

Findings

DG-PIC outperforms state-of-the-art methods across multiple tasks and domains.

It effectively handles unseen domains and multiple tasks simultaneously.

The proposed benchmark facilitates evaluation of multi-task, multi-domain point cloud models.

Abstract

Recent point cloud understanding research suffers from performance drops on unseen data, due to the distribution shifts across different domains. While recent studies use Domain Generalization (DG) techniques to mitigate this by learning domain-invariant features, most are designed for a single task and neglect the potential of testing data. Despite In-Context Learning (ICL) showcasing multi-task learning capability, it usually relies on high-quality context-rich data and considers a single dataset, and has rarely been studied in point cloud understanding. In this paper, we introduce a novel, practical, multi-domain multi-task setting, handling multiple domains and multiple tasks within one unified model for domain generalized point cloud understanding. To this end, we propose Domain Generalized Point-In-Context Learning (DG-PIC) that boosts the generalizability across various tasks and domains at testing time. In particular, we develop dual-level source prototype estimation that considers both global-level shape contextual and local-level geometrical structures for representing source domains and a dual-level test-time feature shifting mechanism that leverages both macro-level domain semantic information and micro-level patch positional relationships to pull the target data closer to the source ones during the testing. Our DG-PIC does not require any model updates during the testing and can handle unseen domains and multiple tasks, \textit{i.e.,} point cloud reconstruction, denoising, and registration, within one unified model. We also introduce a benchmark for this new setting. Comprehensive experiments demonstrate that DG-PIC outperforms state-of-the-art techniques significantly.